Hacker News Reader

Sounds easy! So what does your plan to implement "simple safeguards" for a chatbot on Twitter look like?

For starter: penalizing generated phrases with obscene words, "hate", "kill", "Hilter" and a few other.

"I really hate Hitler. If he were alive today, I'd kill him."

Want to give a reason that should be a heavily penalized phrase?

It's safer to just avoid Hitler altogether.